Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Contrastive Machine Learning to Quantify Hypertensive Multiorgan Damage and Identify New Disease Phenotypes: A Multinational Multimodal Study.

Circulation·2026
Same author

The collection of speech data for the assessment of cognition remotely: Balancing ethical and practical challenges.

Alzheimer's & dementia (Amsterdam, Netherlands)·2026
Same author

Applications of artificial intelligence and computational approaches to imaging for hypertension identification, phenotyping, and outcome prediction: a systematic review.

European heart journal. Digital health·2026
Same author

Improving LIME Stability via Density-Awareness: Evaluation and Comparison of AKDE-LIME.

Applied artificial intelligence : AAI·2026
Same author

Out-of-Distribution Detection in Medical Image Segmentation with <math><mi>β</mi></math> -VAE and Likelihood Regret.

Journal of imaging informatics in medicine·2026
Same author

VarCoNet: A Variability-Aware Self-Supervised Framework for Functional Connectome Extraction From Resting-State fMRI.

Human brain mapping·2026

Related Experiment Video

Updated: Apr 16, 2026

SwarmSight: Real-time Tracking of Insect Antenna Movements and Proboscis Extension Reflex Using a Common Preparation and Conventional Hardware
08:13

SwarmSight: Real-time Tracking of Insect Antenna Movements and Proboscis Extension Reflex Using a Common Preparation and Conventional Hardware

Published on: December 25, 2017

8.8K

Swarm intelligence for detecting interesting events in crowded environments.

Vagia Kaltsa, Alexia Briassouli, Ioannis Kompatsiaris

    IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society
    |March 14, 2015
    PubMed
    Summary
    This summary is machine-generated.

    This study introduces a novel method for detecting unusual events in crowded videos by analyzing motion and appearance. The approach, using histograms of oriented swarms (HOS) and gradients, achieves superior accuracy and efficiency in anomaly detection.

    More Related Videos

    The HoneyComb Paradigm for Research on Collective Human Behavior
    06:48

    The HoneyComb Paradigm for Research on Collective Human Behavior

    Published on: January 19, 2019

    10.0K
    Time-lapse Imaging of Bacterial Swarms and the Collective Stress Response
    06:26

    Time-lapse Imaging of Bacterial Swarms and the Collective Stress Response

    Published on: May 23, 2020

    9.0K

    Related Experiment Videos

    Last Updated: Apr 16, 2026

    SwarmSight: Real-time Tracking of Insect Antenna Movements and Proboscis Extension Reflex Using a Common Preparation and Conventional Hardware
    08:13

    SwarmSight: Real-time Tracking of Insect Antenna Movements and Proboscis Extension Reflex Using a Common Preparation and Conventional Hardware

    Published on: December 25, 2017

    8.8K
    The HoneyComb Paradigm for Research on Collective Human Behavior
    06:48

    The HoneyComb Paradigm for Research on Collective Human Behavior

    Published on: January 19, 2019

    10.0K
    Time-lapse Imaging of Bacterial Swarms and the Collective Stress Response
    06:26

    Time-lapse Imaging of Bacterial Swarms and the Collective Stress Response

    Published on: May 23, 2020

    9.0K

    Area of Science:

    • Computer Vision
    • Artificial Intelligence
    • Pattern Recognition

    Background:

    • Detecting anomalous events in crowded scenes is challenging due to complex dynamics.
    • Existing methods often struggle with robustness and computational efficiency.

    Purpose of the Study:

    • To develop a robust and efficient method for detecting and localizing anomalous events in crowded videos.
    • To improve upon the current state-of-the-art in anomaly detection for dynamic scenes.

    Main Methods:

    • Utilized swarm theory concept: histograms of oriented swarms (HOS) to capture crowd dynamics.
    • Combined HOS with histograms of oriented gradients (HOG) for scene characterization.
    • Extracted features within spatiotemporal volumes of moving pixels for enhanced robustness and efficiency.

    Main Results:

    • Achieved state-of-the-art results on benchmark datasets for both human crowds and traffic scenarios.
    • Demonstrated significantly higher accuracy, particularly in pixel-level event detection.
    • Confirmed the method's efficacy, generality, and low computational cost.

    Conclusions:

    • The proposed method effectively detects and localizes anomalies in crowded scenes.
    • The integration of HOS and HOG features offers a robust and computationally efficient solution.
    • This approach advances the field of anomaly detection in complex dynamic environments.